Generating and executing query language statements from natural language

• US 10,169,471 B2
• Filed: 04/28/2016
• Issued: 01/01/2019
• Est. Priority Date: 07/24/2015
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Dayan, Yigal S., Magdalen, Josemina M., Maharian, Irit, Mazel, Victoria, Paikowsky, Oren, Shtilman, Andrei
• Primary Examiner(s): Arjomandi, Noosha
• Application Number:
  US15/140,839
• Publication Number:
  US 20170024431A1
• Time in Patent Office: 978 Days
• CPC Class Codes: G06F 16/24522 Translation of natural language queries to structured queries
• CPC Class Codes: G06F 16/3338 Query expansion
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

Techniques for generating query language statements for a document repository are described herein. An example method includes detecting a search query corresponding to a document repository and generating a modified search query by adding atomic tags to the search query, the atomic tags being based on prior knowledge obtained by static analysis of the document repository and semantic rules. The method also includes generating enriched tags based on combinations of the atomic tags and any previously identified enriched tags and generating a first set of conditions based on combinations of the atomic tags and the generated enriched tags and generating a second set of conditions based on free-text conditions. The method also includes generating the query language statements based on the first set of conditions and the second set of conditions and displaying a plurality of documents from the document repository that satisfy the query language statements.

Claims

1. A method for generating query language statements for a document repository comprising:

detecting, via a processor, a search query corresponding to a document repository;

generating, via the processor, a modified search query by adding atomic tags to the search query, the atomic tags being based on prior knowledge obtained by static analysis of the document repository and semantic rules;

generating, via the processor, enriched tags based on combinations of the atomic tags and any previously identified enriched tags and adding the generated enriched tags to the modified search query;

generating, via the processor, a first set of conditions based on combinations of the atomic tags and the generated enriched tags and generating a second set of conditions based on free-text conditions, the second set of conditions corresponding to terms in the search query that are not associated with any of the first set of conditions;

reconciling, via the processor, the first set of conditions based on identified contradictions;

generating, via the processor, the query language statements corresponding to the search query, the query language statements based in part on the first set of conditions and the second set of conditions; and

displaying, via the processor, a plurality of documents from the document repository that satisfy the query language statements, wherein

the generating the query language statements comprises;

joining at least two queries for documents of a same type with a logical disjunction or at least two queries for documents of a different type with a logical conjunction.

2. The method of claim 1, wherein the query language statements correspond to a score based on a characteristic of the search query.

3. The method of claim 2, wherein the score indicates that the search query references a field search term or a document search term, the score indicating a preference for search query language statements that correspond to the field search term.

4. The method of claim 1, further comprising identifying the atomic tags from an entity list, the entity list comprising the prior knowledge obtained by static analysis of the document repository.

5. The method of claim 1, further comprising generating the semantic rules, each semantic rule indicating an action, the action comprising generating a new atomic tag or generating a condition.

6. The method of claim 5, further comprising:

determining that results of the query language statements do not exceed a quality threshold;

generating relaxation rules; and

modifying the query language statements based on the relaxation rules.

7. The method of claim 5, wherein the query language statements correspond to a score based on a characteristic of the search query.

8. The method of claim 7, wherein the score indicates that the search query references a field search term or a document search term, the score indicating a preference for search query language statements that correspond to the field search term.

9. The method of claim 5, further comprising identifying the atomic tags from an entity list, the entity list comprising the prior knowledge obtained by static analysis of the document repository.

10. The method of claim 1, further comprising:

translating the first set of conditions and the second set of conditions into the query language statements corresponding to the document repository.